🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

📢 Update: We've deepened our exploration of VLMs on Bongard Problems with more rigorous evaluations! The best-performing model (o1) we tested solved 43 out of 100 problems - progress, but still plenty of room for improvement!

📢Call for Papers – HLDM 2025 @ ECML-PKDD Submit your work on hybrid human-machine decision making: human-in-the-loop ML, trust, ethics, cognition! 🗓️ Deadline: June 14, 2025 📍 Barcelona 🔗More info: sml.disi.unitn.it/hldm25.html #HLDM2025 #AI #ML #HumanAI #CFP #ECMLPKDD

🔥"Where is the Truth? The Risk of Getting Confounded in a Continual World" got a spotlight poster ICML Conference ! arxiv.org/abs/2402.06434 -> we introduce continual confounding + the ConCon dataset, where confounders over time render continual knowledge accumulation insufficient⬇️

To appear at ICML 2025 (ICML Conference) as a spotlight! 🚀🚀🚀

Now in Thailand to present our paper at #AISTATS2025 🇹🇭🌴 📍Today at 3:00-6:00 pm, poster number 118! More details here: openreview.net/forum?id=XCmIl…

Excited to share that our paper “Rethinking and Recomputing the Value of Machine Learning Models” has been accepted to the Journal of Artificial Intelligence Review, and it is accessible online 🎉 link.springer.com/article/10.100… #MachineLearning #AI

🚨Our paper “Bringing Machine Learning Classifiers Into Critical Cyber-Physical Systems: a Matter of Design” has been accepted to IEEE Access and preprint is available in Early Access! Please check it out: ieeexplore.ieee.org/document/10994… andrea passerini

One more week to apply to this exciting position... and another position on #CausalRepresentationLearning and #ReinforcementLearning for learning provably correct #concepts from raw data opening up soon!

Got a great causality-related idea? 🇧🇷 Don’t miss the chance to present your work in Rio for the CAR Workshop at #uai2025! 🔥 We welcome works in causal abstraction, representation learning, clustered graphs, and more! 🗓️ Deadline: May 26, 2025

We propose Neurosymbolic Diffusion Models! We find diffusion is especially compelling for neurosymbolic approaches, combining powerful multimodal understanding with symbolic reasoning 🚀 Read more 👇

Early bird registration deadline is next Monday 2nd of June 🏃‍♂️ you can register to attend in person or as virtual participants! ⚡ auai.org/uai2025/regist… ⚡

🔥 Curious about where machine learning meets network science? Join our panel at #NetSci2025 as ML pros and network scientists tackle the big questions: When? Why? How? Discover how these worlds collide—and how to make the most of it. Don't miss out!

Ringrazio Radio 3 Mondo per lo spazio che mi ha voluto concedere. Sempre felice di intervenire.

Are you based in Greece? 🇬🇷 Do you want to attend #FAccT2025 and have your entire registration fee waived? Volunteer for just 4 hours at the conference! Apply by June 3, 2025, at 11:59 pm anywhere on Earth: facctconference.org/2025/cfv2

AI models are rewriting their own shutdown code My op-ed in The Wall Street Journal today explains why alignment is now a national security race: 🧵

🚨 Deadline extended! 🚨 Submit to HLDM'25 (Hybrid Human-Machine Learning & Decision Making) Workshop @ ECML-PKDD by June 21, 2025! 📄 Short, regular & non-archival papers welcome! Check our website: sml.disi.unitn.it/hldm25.html andrea passerini TANGO #AI #ML

Last few days to apply to this PhD position 🌷🚲🇳🇱 deadline is June 15th

What? Identifiability and LLMs all in one paper?😱 👇 👇 👇

Many people assume that LRM reasoning breaks down past a certain "complexity" or "number of steps" threshold. This is incorrect. It breaks down past an unfamiliarity threshold. And that threshold is very low. There is no limit to the complexity of tasks you can solve with these

Had a great time yesterday afternoon presenting our poster on Multi-focal Conditioned Image Synthesis with Nicu! Huge credit to Jiaqi, our first author, whose excellent work made it all possible, but could not come to #CVPR2025 👏🧠🖼️